# US 2023/0410211 A1 · Machine-learning driven real-time data analysis

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0410211 A1
- Document ID: US20230410211A1
- Status: Published application
- Kind: A1
- Application number: 18/363,299
- Filed: 2023-08-01
- Published: 2023-12-21
- Earliest claimed: 2021-04-13
- Assignees: Nayya Health, Inc.
- Applicants: Nayya Health, Inc.
- Inventors: Sina CHEHRAZI; John Joseph GLORIOSO, JR.; Akash MAGOON; Aman MAGOON
- Web page: https://patentgrep.com/patent/US20230410211A1

## CPC

- G06Q 40/08: Insurance
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06Q 10/10: Office automation; Time management
- G06Q 50/00: Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism (healthcare informatics G16H)
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 40/20: for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 20/10: relating to drugs or medications, e.g. for ensuring correct administration to patients
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

A data processing system for insurance claims analysis and adjudication implements obtaining policy coverage information for each of a plurality of insurance policies and insurance claim information associated with a plurality of insurance claims associated with an insured user, analyzing the insurance claim information using a first machine learning to obtain event-related claim grouping information; analyzing the event-related claim grouping information and the standardized policy information using the second machine learning model to obtain coverage prediction information comprising a prediction, for each event of the one or more events, identifying a respective insurance policy of the plurality of insurance policies likely to cover the one or more claims associated with each event, the second machine learning model being trained using second training data formatted according to the standard schema; and providing, via a network connection, the coverage prediction information to a computing device associated with the insured user.

## Claims

### Claim 1

A data processing system comprising:
a processor; and
a machine-readable medium storing executable instructions that, when executed, cause the processor alone or in combination with other processors to perform operations comprising:
obtaining policy coverage information for each of a plurality of insurance policies associated with an insured user, the policy coverage information being in one or more first formats;
generating standardized policy coverage information from the policy coverage information by converting the policy coverage information from the one or more first formats to a standardized format according to a standard schema for processing policy and claim information;
obtaining insurance claim information associated with a plurality of insurance claims associated with the insured user, the insurance claim information being in one or more second formats;
generating standardized insurance claim information from the insurance claim information by converting insurance claim information from the one or more second formats to the standardized format according to the standard schema;
providing the standardized insurance claim information as an input to a claims grouping model trained with first training data formatted according to the standard schema to recognize patterns in insurance claim information indicative of an occurrence of specific types of events requiring medical treatment;
analyzing the standardized insurance claim information with the claims grouping model to obtain event-related claim grouping information, the event-related claim grouping information including an indication of one or more events predicted to have occurred based on the standardized insurance claim information and one or more insurance claims of the plurality of insurance claims included in the standardized insurance claim information predicted to be associated with each event of the one or more events;
providing the event-related claim grouping information and the standardized policy information as an input to a coverage prediction model trained using second training data formatted according to the standard schema;
analyzing the event-related claim grouping information and the standardized policy information using the coverage prediction model to obtain coverage prediction information comprising a prediction, for each event of the one or more events, identifying a respective insurance policy of the plurality of insurance policies included in the standardized policy coverage information predicted to cover the one or more claims associated with each event; and
providing, via a network connection, the coverage prediction information to a computing device associated with the insured user.

### Claim 2 (depends on 1)

The data processing system of claim 1, wherein the coverage prediction model is further trained to analyze coverage limitations associated with each respective policy of the plurality of insurance policies when predicting the respective insurance policy of the plurality of insurance policies is likely to cover the one or more claims associated with an event.

### Claim 3 (depends on 2)

The data processing system of claim 2, wherein the coverage prediction model is further trained to consider how much of the coverage limitations associated with the respective policy of the plurality of insurance policies has already been utilized when predicting the respective insurance policy of the plurality of insurance policies is likely to cover the one or more claims associated with the respective event.

### Claim 4 (depends on 1)

The data processing system of claim 1, wherein generating the standardized insurance claim information from the insurance claim information further comprises:
performing a fuzzy match on information associated with each insurance claim with a standard set of claim descriptions to identify a standard description for the insurance claim; and
adding the standard description to the standardized insurance claim information.

### Claim 5 (depends on 1)

The data processing system of claim 1, wherein the coverage prediction model outputs a confidence score for each prediction, and wherein the machine-readable medium includes instructions configured to cause the processor to perform:
receiving a first prediction associated with a first event of the one or more events and a first confidence score associated with the first prediction from the coverage prediction model;
responsive to the first confidence score not satisfying a confidence threshold, dynamically generating a set of questions to obtain additional information from the insured user for the one or more insurance claims associated with the first event;
providing the dynamically generated set of questions to the computing device associated with the insured user; and
obtaining user response information from the computing device associated with the insured user in response to the dynamically generated set of questions.

### Claim 6 (depends on 5)

The data processing system of claim 5, wherein the machine-readable medium includes instructions configured to cause the processor to perform:
providing the event-related claim grouping information, the standardized policy information, and the user response information as an input to the coverage prediction model;
analyzing the event-related claim grouping information, the standardized policy information, and the user response information with the coverage prediction model to obtain a second prediction and a second confidence score from the coverage prediction model; and
providing the prediction to the computing device associated with the insured user responsive to the second confidence score satisfying the confidence threshold.

### Claim 7 (depends on 1)

The data processing system of claim 1, wherein the machine-readable medium includes instructions configured to cause the processor alone or in combination with other processors to perform:
causing a user interface to be shown on a display of the computing device associated with the insured user to present the coverage prediction information, the user interface being configured to, for each respective event of the one or more events, guide the user through submitting the one or more insurance claims associated with the respective event to an insurance provider associated with a respective policy predicted as being likely to cover the one or more claims associated with the respective event.

### Claim 8

A method implemented in a data processing system for insurance claims analysis and adjudication, the method comprising:
obtaining policy coverage information for each of a plurality of insurance policies associated with an insured user, the policy coverage information being in one or more first formats;
generating standardized policy coverage information from the policy coverage information by converting the policy coverage information from the one or more first formats to a standardized format according to a standard schema for processing policy and claim information;
obtaining insurance claim information associated with a plurality of insurance claims associated with the insured user, the insurance claim information being in one or more second formats;
generating standardized insurance claim information from the insurance claim information by converting insurance claim information from the one or more second formats to the standardized format according to the standard schema;
providing the standardized insurance claim information as an input to a claims grouping model trained with first training data formatted according to the standard schema to recognize patterns in insurance claim information indicative of an occurrence of specific types of events requiring medical treatment;
analyzing the standardized insurance claim information with the claims grouping model to obtain event-related claim grouping information, the event-related claim grouping information including an indication of one or more events predicted to have occurred based on the standardized insurance claim information and one or more insurance claims of the plurality of insurance claims included in the standardized insurance claim information predicted to be associated with each event of the one or more events;
providing the event-related claim grouping information and the standardized policy information as an input to a coverage prediction model trained using second training data formatted according to the standard schema;
analyzing the event-related claim grouping information and the standardized policy information using the coverage prediction model to obtain coverage prediction information comprising a prediction, for each event of the one or more events, identifying a respective insurance policy of the plurality of insurance policies included in the standardized policy coverage information predicted to cover the one or more claims associated with each event; and
providing, via a network connection, the coverage prediction information to a computing device associated with the insured user.

### Claim 9 (depends on 8)

The method of claim 8, wherein the coverage prediction model is further trained to analyze coverage limitations associated with each respective policy of the plurality of insurance policies when predicting the respective insurance policy of the plurality of insurance policies is likely to cover the one or more claims associated with the respective event.

### Claim 10 (depends on 9)

The method of claim 9, wherein the coverage prediction model is further trained to consider how much of the coverage limitations associated with the respective policy of the plurality of insurance policies has already been utilized when predicting the respective insurance policy of the plurality of insurance policies is likely to cover the one or more claims associated with the respective event.

### Claim 11 (depends on 8)

The method of claim 8, wherein generating the standardized insurance claim information from the insurance claim information further comprises:
performing a fuzzy match on information associated with each insurance claim with a standard set of claim descriptions to identify a standard description for the insurance claim; and
adding the standard description to the standardized insurance claim information.

### Claim 12 (depends on 8)

The method of claim 8, wherein the coverage prediction model outputs a confidence score for each prediction, and the method further comprising:
receiving a first prediction associated with a first event of the one or more events and a first confidence score associated with the first prediction from the coverage prediction model;
responsive to the first confidence score not satisfying a confidence threshold, dynamically generating a set of questions to obtain additional information from the insured user for the one or more insurance claims associated with the first event;
providing the dynamically generated set of questions to the computing device associated with the insured user; and
obtaining user response information from the computing device associated with the insured user in response to the dynamically generated set of questions.

### Claim 13 (depends on 12)

The method of claim 12, further comprising:
providing the event-related claim grouping information, the standardized policy information, and the user response information as an input to the coverage prediction model;
analyzing the event-related claim grouping information, the standardized policy information, and the user response information with the coverage prediction model to obtain a second prediction and a second confidence score from the coverage prediction model; and
providing the prediction to the computing device associated with the insured user responsive to the second confidence score satisfying the confidence threshold.

### Claim 14 (depends on 8)

The method of claim 8, further comprising:
causing a user interface to be shown on a display of the computing device associated with the insured user to present the coverage prediction information, the user interface being configured to, for each respective event of the one or more events, guide the user through submitting the one or more insurance claims associated with the respective event to an insurance provider associated with a respective policy predicted as being likely to cover the one or more claims associated with the respective event.

### Claim 15

A machine-readable medium on which are stored instructions that, when executed, cause a processor of a programmable device alone or in combination with other processors to perform operations of:
obtaining policy coverage information for each of a plurality of insurance policies associated with an insured user, the policy coverage information being in one or more first formats;
generating standardized policy coverage information from the policy coverage information by converting the policy coverage information from the one or more first formats to a standardized format according to a standard schema for processing policy and claim information;
obtaining insurance claim information associated with a plurality of insurance claims associated with the insured user, the insurance claim information being in one or more second formats;
generating standardized insurance claim information from the insurance claim information by converting insurance claim information from the one or more second formats to the standardized format according to the standard schema;
providing the standardized insurance claim information as an input to a claims grouping model trained with first training data formatted according to the standard schema to recognize patterns in insurance claim information indicative of an occurrence of specific types of events requiring medical treatment;
analyzing the standardized insurance claim information with the claims grouping model to obtain event-related claim grouping information, the event-related claim grouping information including an indication of one or more events predicted to have occurred based on the standardized insurance claim information and one or more insurance claims of the plurality of insurance claims included in the standardized insurance claim information predicted to be associated with each event of the one or more events;
providing the event-related claim grouping information and the standardized policy information as an input to a coverage prediction model trained using second training data formatted according to the standard schema;
analyzing the event-related claim grouping information and the standardized policy information using the coverage prediction model to obtain coverage prediction information comprising a prediction, for each event of the one or more events, identifying a respective insurance policy of the plurality of insurance policies included in the standardized policy coverage information predicted to cover the one or more claims associated with each event; and
providing, via a network connection, the coverage prediction information to a computing device associated with the insured user.

### Claim 16 (depends on 15)

The machine-readable medium of claim 15, wherein the coverage prediction model is further trained to analyze coverage limitations associated with each respective policy of the plurality of insurance policies when predicting the respective insurance policy of the plurality of insurance policies is likely to cover the one or more claims associated with an event.

### Claim 17 (depends on 16)

The machine-readable medium of claim 16, wherein the coverage prediction model is further trained to consider how much of the coverage limitations associated with the respective policy of the plurality of insurance policies has already been utilized when predicting the respective insurance policy of the plurality of insurance policies is likely to cover the one or more claims associated with the respective event.

### Claim 18 (depends on 15)

The machine-readable medium of claim 15, wherein generating the standardized insurance claim information from the insurance claim information further comprises:
performing a fuzzy match on information associated with each insurance claim with a standard set of claim descriptions to identify a standard description for the insurance claim; and
adding the standard description to the standardized insurance claim information.

### Claim 19 (depends on 15)

The machine-readable medium of claim 15, wherein the coverage prediction model is configured to output a confidence score for each prediction, and wherein the machine-readable medium further comprises instructions configured to cause the processor alone or in combination with other processors to perform:
receiving a first prediction associated with a first event of the one or more events and a first confidence score associated with the first prediction from the coverage prediction model;
responsive to the first confidence score not satisfying a confidence threshold, dynamically generating a set of questions to obtain additional information from the insured user for the one or more insurance claims associated with the first event;
providing the dynamically generated set of questions to the computing device associated with the insured user;
obtaining user response information from the computing device associated with the insured user in response to the dynamically generated set of questions;
providing the event-related claim grouping information, the standardized policy information, and the user response information as an input to the coverage prediction model;
analyzing the event-related claim grouping information, the standardized policy information, and the user response information with the coverage prediction model to obtain a second prediction and a second confidence score from the coverage prediction model; and
providing the prediction to the computing device associated with the insured user responsive to the second confidence score satisfying the confidence threshold.

### Claim 20 (depends on 15)

The machine-readable medium of claim 15, wherein further comprising instructions configured to cause the processor alone or in combination with other processors to perform:
causing a user interface to be shown on a display of the computing device associated with the insured user to present the coverage prediction information, the user interface being configured to, for each respective event of the one or more events, guide the user through submitting the one or more insurance claims associated with the respective event to an insurance provider associated with a respective policy predicted as being likely to cover the one or more claims associated with the respective event.
